Knowledge Distillation

Bridging Relevance and Reasoning: Rationale Distillation in Retrieval-Augmented Generation ACL 2025 Building Resource-Constrained Language Agents: A Korean Case Study on Chemical Toxicity Information EMNLP 2025 Cache-of-Thought: Master-Apprentice Framework for Cost-Effective Vision Language Model Reasoning EMNLP 2025 CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images CVPR 2025 CAKE: Category Aware Knowledge Extraction for Open-Vocabulary Object Detection AAAI 2025 Can Large Language Models Act as Ensembler for Multi-GNNs? EMNLP 2025 Can Students Beyond the Teacher? Distilling Knowledge from Teacher’s Bias AAAI 2025 Can We Achieve Efficient Diffusion Without Self-Attention? Distilling Self-Attention into Convolutions ICCV 2025 Capture the Key in Reasoning to Enhance CoT Distillation Generalization ACL 2025 CARMO: Dynamic Criteria Generation for Context Aware Reward Modelling ACL 2025 CEMIL: Contextual Attention Based Efficient Weakly Supervised Approach for Histopathology Image Classification WACV 2025 Chain-of-Thought Distillation with Fine-Grained Acoustic Cues for Speech Emotion Recognition Interspeech 2025 ChromaDistill : Colorizing Monochrome Radiance Fields with Knowledge Distillation WACV 2025 Classifier-guided CLIP Distillation for Unsupervised Multi-label Classification CVPR 2025 CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discrimination AAAI 2025 CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation EMNLP 2025 Co-distilled attention guided masked image modeling with noisy teacher for self-supervised learning on medical images MIDL 2025 Combining Inherent Knowledge of Vision-Language Models with Unsupervised Domain Adaptation through Strong-Weak Guidance WACV 2025 CoMBO: Conflict Mitigation via Branched Optimization for Class Incremental Segmentation CVPR 2025 Comparative Knowledge Distillation WACV 2025 Comprehensive and Efficient Distillation for Lightweight Sentiment Analysis Models EMNLP 2025 ConDo: Continual Domain Expansion for Absolute Pose Regression AAAI 2025 Co-Progression Knowledge Distillation with Knowledge Prototype for Industrial Anomaly Detection AAAI 2025 Coupling the Generator with Teacher for Effective Data-Free Knowledge Distillation ICCV 2025 Cross-Modal Distillation for 2D/3D Multi-Object Discovery from 2D Motion CVPR 2025